Custom Software Engineering Lead

Project Role : Custom Software Engineering Lead
Project Role Description : Own the technical direction and architecture of custom software solutions, leading teams through design and delivery. Set development standards and ensure code quality, scalability, and performance aligned to business objectives.
Must have skills : Generative AI
Good to have skills : NA
Minimum 7.5 year(s) of experience is required
Educational Qualification : 15 years full time education
Summary:
As a Custom Software Engineering Lead, a typical day involves overseeing the technical direction and architectural design of bespoke software solutions. This role requires guiding teams through the entire development lifecycle, from initial design concepts to final delivery. The position demands setting and maintaining high standards for development practices, ensuring that the software produced is scalable, performs efficiently, and aligns closely with the strategic goals of the organization. Collaboration and leadership are central to managing the workflow and fostering an environment where innovation and quality thrive.

Roles & Responsibilities:
-Define and own the AI/GenAI solution architecture for PLM engagements — covering RAG pipelines, agentic workflows, LLM orchestration patterns, and integration with enterprise PLM systems.
-Set the technical strategy for LLM selection across the engagement — evaluating Claude, GPT-4, and open-source models against context length, cost, latency, compliance, and PLM-specific requirements define token budgets, caching strategy, and batch vs. real-time decisions at design time.
Design RAG approaches — chunking strategy, embedding model selection, vector store architecture, hybrid search, and re-ranking — and govern the quality and evaluation standards of what the delivery team builds.
-Lead the MCP (Model Context Protocol) strategy — define governance and standards for MCP usage across the team, oversee integration of MCP servers into agentic workflows, and guide the building of custom MCP servers leverage Claude's native MCP support for Claude-powered enterprise solutions.
Own CLAUDE.md project-level governance — define team-wide Claude Code rules, hooks, and workflow standards so the entire squad works consistently within a governed AI development environment.
-Actively contribute to hands-on delivery — prototype, code review, and set coding standards — while guiding the technical output of Level 9 engineers this is a hands-on architecture role with significant time expected in code.
Define and oversee AI evaluation and observability standards across the engagement — RAG quality metrics, output monitoring, hallucination tracking, and production drift alerting.
-Embed AI risk and responsible AI thinking into solution design — data residency, PII handling, model output governance, and enterprise AI compliance frameworks.
-Lead client workshops, architecture reviews, and stakeholder discussions up to CTO/VP level translate business and PLM requirements into AI solution blueprints support pre-sales and proposal development including solution scoping and estimation for AI workloads.
-Mentor Level 9 engineers contribute reusable assets, accelerators, and playbooks — such as RAG evaluation templates and agentic workflow patterns — to Accenture's internal AI CoE.

Professional & Technical Skills:
- Must To Have Skills: Proficiency in Generative AI.
-Anthropic SDK — deep proficiency with the Anthropic Python and TypeScript SDKs messages API, streaming, async patterns, tool use schema definition, and the Batch API ability to define SDK usage standards across the delivery team.
LLMs & Prompt Engineering — deep hands-on experience across Claude (Haiku / Sonnet / Opus), GPT-4, Gemini, LLaMA ability to define model selection strategy across an engagement based on context window, cost, latency, and enterprise compliance few-shot, chain-of-thought, and structured JSON outputs.
-Claude-Specific Capabilities — prompt caching, extended thinking, tool use / function calling, 200K token context window utilisation for large PLM documents deep understanding of Claude's strengths in long-document reasoning and instruction-following in enterprise contexts.
-Claude Code — experience using Claude Code as an agentic development environment ability to define and govern project-level instructions via CLAUDE.md / Rules for the entire delivery team, design pre/post tool execution automation using Hooks, build custom multi-step workflows, and run Claude Code in headless / CI mode for automated engineering pipelines.
-Embedding Models — experience selecting and benchmarking embedding models (BGE, E5, sentence-transformers, Cohere, OpenAI Ada / text-embedding-3 series) for domain-specific engineering vocabulary ability to define embedding strategy at engagement level.
-RAG — end-to-end RAG architecture design chunking strategies, vector stores (FAISS, Pinecone, Weaviate, Chroma, pgvector), hybrid search, re-ranking (cross-encoders, Cohere Rerank) ability to set quality standards and review pipeline implementations.
-Agentic Frameworks — LangChain / LangGraph / AutoGen tool-calling, memory, multi-step agent loops structured output validation ability to define agentic architecture patterns for the team.
-MCP (Model Context Protocol) — architectural understanding of the protocol ability to build and govern custom MCP servers define MCP standards and usage governance across the delivery team ability to assess MCP integration patterns for enterprise security and scalability.
-LLM Evaluation & Observability — experience with evaluation frameworks (Ragas, TruLens, ARES) and tracing / monitoring tools (LangSmith, Arize, Helicone) ability to define engagement-wide eval standards, golden datasets, and production monitoring thresholds.
-Python — FastAPI / Flask, LangChain, Pydantic, Pandas REST API development streaming and async patterns Git & CI/CD code review and standards setting.
-Cloud — Azure / AWS / GCP AI services Docker / Kubernetes MLOps pipelines.
PLM — solution design against PLM architecture BOM structures, ECO/ECR workflows, configuration management integration patterns with Teamcenter, Windchill, or 3DEXPERIENCE ability to engage PLM architects and client leads at technical depth.
-Node.js / TypeScript — basic frontend AI integrations is a plus.

Additional Information:
- The candidate should have minimum 8+ years overall experience 5+ in AI/ML production 3+ in GenAI. Proven experience delivering AI solutions in an engineering or PLM context is a strong plus. Consulting or client-facing experience preferred.
-AWS ML Specialty / Azure AI Engineer Associate / Google Professional ML Engineer.
-Deep Learning or NLP Specialization (deeplearning.ai).
-LangChain or Hugging Face certifications where available.
-PLM platform certifications (Enovia, Teamcenter, Windchill) are a bonus.
- This position is based at our Bengaluru office.
- A 15 years full time education is required.

15 years full time education

About Accenture

Accenture is a leading global professional services company that helps the world’s leading businesses, governments and other organizations build their digital core, optimize their operations, accelerate revenue growth and enhance citizen services—creating tangible value at speed and scale. We are a talent- and innovation-led company with approximately 791,000 people serving clients in more than 120 countries. Technology is at the core of change today, and we are one of the world’s leaders in helping drive that change, with strong ecosystem relationships. We combine our strength in technology and leadership in cloud, data and AI with unmatched industry experience, functional expertise and global delivery capability. Our broad range of services, solutions and assets across Strategy & Consulting, Technology, Operations, Industry X and Song, together with our culture of shared success and commitment to creating 360° value, enable us to help our clients reinvent and build trusted, lasting relationships. We measure our success by the 360° value we create for our clients, each other, our shareholders, partners and communities.

Visit us at www.accenture.com 

Equal Employment Opportunity Statement

We believe that no one should be discriminated against because of their differences. All employment decisions shall be made without regard to age, race, creed, color, religion, sex, national origin, ancestry, disability status, military veteran status, sexual orientation, gender identity or expression, genetic information, marital status, citizenship status or any other basis as protected by applicable law. Our rich diversity makes us more innovative, more competitive, and more creative, which helps us better serve our clients and our communities.