The Role
Build and deploy production-grade LLM applications, AI agents, models, and scalable RAG pipelines for investment and business workflows. Architect secure MCP integrations with enterprise systems, establish MLOps and LLMOps practices, optimize model performance and latency, and develop evaluation, monitoring, governance, and rollback processes. Collaborate with data engineering and platform teams to provide secure, governed access to organizational data.
Summary Generated by Built In
This is a remote position.
We're looking for an exceptionally sharp AI Engineer or Senior Data Scientist to join and help us build the next generation of intelligent, data-driven products. You'll architect and ship production-grade LLM applications, design RAG pipelines that actually work at scale, and bring rigorous ML thinking to everything from prompt design to system evaluation. This is a high-autonomy, high-impact role — you'll work closely with product and engineering to own problems end-to-end.
- Design, build, and deploy AI models, tools, and agents to automate intelligence-heavy workflows in investment research, portfolio management, operations, and client reporting.
- Partner with the Head of Data & AI to define the technical architecture for AI use cases, integrating with Snowflake, Databricks, internal APIs, and event streams in a secure and governed way.
- Implement retrieval augmented generation (RAG) pipelines and prompt conditioning patterns that ground LLMs on Marathon’s proprietary data, documents, and knowledge assets.
- Design and implement Model Context Protocol (MCP)–based integrations so AI assistants and agents can securely discover and connect to internal systems, databases, and services through standardized MCP servers and clients.
- Build and maintain MCP servers that wrap key enterprise services (data warehouses, document stores, workflow systems) and expose tools, resources, and prompts to AI clients in a standardized way.
- Establish patterns for MCP host/client configuration, access control, and observability to ensure reliable, auditable AI interactions with enterprise systems.
- Implement MLOps and LLMOps practices for both model and MCP-based integration lifecycles, including deployment automation, monitoring, logging, and rollback strategies.
- Collaborate with data engineers and platform teams to ensure clean, secure, and well-structured data access for AI consumption, including governance of which systems are exposed via MCP.
Requirements
Core skills we need
Python (expert)
LLMs & GenAI
RAG systems
Prompt engineering
AWS
ML / MLOps
Vector DBs
Model versioning
REST APIs
Docker / containers
Requirements
- 6+ years of hands-on Python — you write production code, build packages, and care about performance and readability.
- Proven experience building and shipping LLM-powered applications (not just wrappers — you understand what's happening under the hood).
- Deep understanding of RAG: dense retrieval, sparse retrieval, hybrid, re-ranking, context window management, and evaluation.
- Strong prompt engineering skills: you know when to use CoT, how to design structured outputs, and how to debug hallucinations systematically.
- Hands-on AWS experience — SageMaker, S3, Lambda, CloudWatch, and ideally Bedrock or SageMaker JumpStart.
- Solid ML fundamentals: model training, evaluation, bias/variance, feature engineering, and experimental design.
- Comfortable with embedding models, tokenization internals, KV-cache, quantization trade-offs, and latency optimization.
Nice to have
- Experience with agentic frameworks (LangChain, LlamaIndex, CrewAI, or custom tool-use implementations).
- Fine-tuning experience — LoRA, QLoRA, instruction tuning, RLHF familiarity.
- Familiarity with evaluation frameworks: RAGAS, DeepEval, or building custom eval harnesses.
- MLOps tooling: MLflow, DVC, Weights & Biases, or SageMaker Pipelines.
- Knowledge of streaming inference, async serving, and cost optimization for token-heavy workloads.
- Prior work in analytics, BI, or domain-specific NLP (finance, healthcare, e-commerce).
Skills Required
- Expert-level Python with 6+ years of hands-on production experience
- Experience building and shipping LLM-powered applications
- Deep understanding of RAG systems, retrieval, reranking, context management, and evaluation
- Strong prompt engineering skills, including structured outputs and hallucination debugging
- Hands-on AWS experience, including SageMaker, S3, Lambda, and CloudWatch
- Solid machine learning fundamentals, including model training, evaluation, bias and variance, feature engineering, and experimental design
- Knowledge of embedding models, tokenization, KV-cache, quantization, and latency optimization
- Experience with agentic frameworks such as LangChain, LlamaIndex, CrewAI, or custom tool-use implementations
- Fine-tuning experience with LoRA, QLoRA, instruction tuning, or RLHF
- Familiarity with RAGAS, DeepEval, or custom evaluation harnesses
- Experience with MLflow, DVC, Weights & Biases, or SageMaker Pipelines
- Knowledge of streaming inference, asynchronous serving, and token cost optimization
- Prior analytics, business intelligence, or domain-specific NLP experience
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
Simpliigence is an architecture-first Salesforce consulting partner that helps enterprises and high-growth businesses with end-to-end Salesforce implementation, integration, and managed services. The company also provides ERP integration, Salesforce talent placement, and staffing solutions for consultants, developers, architects, administrators, and other specialists. Its work focuses on helping organizations execute digital transformations and improve business processes through Salesforce and related enterprise technologies.
