The Role
Mentored AI engineering internship focused on building production-grade agentic AI systems. Interns will contribute to multi-agent workflows, context management, LLM integration, retrieval, evaluation, governance, and deployment-related tasks using Python and modern AI frameworks. Responsibilities include implementing stateful workflows, structured outputs, tool calling, vector search, verification gates, observability, and model-routing experiments while participating in design and code reviews.
Summary Generated by Built In
AI Engineer Intern
Role Summary
We are looking for five AI Engineering Interns to learn and contribute to production-grade agentic AI systems alongside our engineers. This is a hands-on, mentored internship centred on multi-agent orchestration, context management, and large language model (LLM) integration. It is open to final-year students and recent graduates — what matters most is outstanding computer-science fundamentals, strong data structures and algorithms (DSA) skills, and hands-on ability with Python.
You will work under the guidance of senior engineers on agent workflows and the context architecture behind them, contributing to real features while building production-grade skills. The ideal intern has a strong academic record, sharp problem-solving ability, genuine enthusiasm for the agentic AI stack, and the drive to convert this internship into a full-time AI Engineer role.
Key Responsibilities
Agent Orchestration & Workflow
- Assist in designing and implementing multi-agent workflows using LangGraph on Python with Pydantic structured output, under the guidance of senior engineers.
- Help model processes as stateful, resumable graphs with branching, looping, retries, and checkpointing.
- Support implementation of safe pause/resume and human-in-the-loop (HITL) checkpoints.
Context Engineering
- Learn and contribute to context management — layered context, retrieval/indexing, and active working sets.
- Help implement context selectors and filters, token-budgeted prompts, and summarisation/compaction of long histories.
- Assist in designing typed context schemas so each agent step receives precise, high-signal context.
LLM Integration & Retrieval
- Integrate LLM providers (e.g. Anthropic, OpenAI / Azure OpenAI) using prompt engineering, tool calling, and structured output, with mentorship.
- Help wire in retrieval — vector search and embeddings — and code-intelligence techniques for working over large codebases.
- Contribute to model-routing experiments that balance task type, latency, and cost.
Quality, Evaluation & Governance
- Help build evaluation and error-analysis loops; learn to treat failures as feedback that improves reliability.
- Assist in implementing verification and validation patterns and deterministic gates for agent outputs.
- Help keep agent decisions and context observable, auditable, and reproducible.
Collaboration
- Work with platform/infrastructure engineers on deployment, inference, and persistence tasks.
- Participate in design reviews, code reviews, and Demo Friday — sharing your work, including failed experiments.
Required Technical Skills
DomainSkills & TechnologiesMust / PreferredCS Fundamentals & DSAData structures, algorithms, complexity analysis, strong problem-solvingMustProgrammingPython 3.10+ (async, typing); clean, idiomatic codeMustAgent OrchestrationLangGraph — graphs/state machines, checkpointers, HITL interruptsGood to haveContext EngineeringLayered context, selectors/filters, summarisation & compaction, token budgetingGood to haveAgentic AI DevelopmentMulti-agent design, tool calling, structured output, verification patternsGood to haveLLM IntegrationAnthropic & OpenAI / Azure OpenAI SDKs, prompt engineeringPreferredData ModellingPydantic v2, JSON Schema / typed contractsPreferredRetrievalVector stores (e.g. Qdrant / Azure AI Search), embeddingsPreferredContext ProtocolModel Context Protocol (MCP) — resources/tools, Streamable HTTPPreferredMulti-agent FrameworksCrewAI, Microsoft Agent FrameworkPreferredDurable WorkflowsTemporal (long-running, resumable flows)PreferredInferencevLLM awareness (paged attention, batching, quantisation), model routingPreferredQualifications & Certifications
- Pursuing or recently completed B.Tech / B.E. / M.Tech / MCA in Computer Science or a related field from a reputable institution (or equivalent).
- Final-year students and recent graduates welcome; strong fundamentals matter more than years of experience.
- Strong data structures, algorithms, and problem-solving skills — a competitive-programming track record (Codeforces / LeetCode / ICPC / similar) is a strong plus.
- Hands-on Python, plus any exposure to LLM / agentic AI through academic projects or self-learning — with clear eagerness to go deep on LangGraph and context engineering.
Preferred Certifications
- Any recognised AI/ML or agentic-AI online course or certification (e.g. DeepLearning.AI, Anthropic, Microsoft Azure AI Fundamentals).
- Any cloud fundamentals certification (Azure / AWS / GCP) is a plus.
Soft Skills & Cultural Fit
- Strong analytical mindset with a structured approach to design, debugging, and root-cause analysis.
- Clear written and verbal communication — able to explain your approach to technical and non-technical people.
- Eagerness to learn, high coachability, and the ability to take and act on feedback.
- Collaborative team player who contributes to shared standards, code reviews, and knowledge sharing.
Skills Required
- Pursuing or recently completed a B.Tech, B.E., M.Tech, MCA, or equivalent degree in Computer Science or a related field
- Strong computer science fundamentals, including data structures, algorithms, complexity analysis, and problem-solving
- Hands-on ability with Python 3.10+ and clean, idiomatic code
- Strong analytical mindset and structured approach to design, debugging, and root-cause analysis
- Clear written and verbal communication skills
- Collaborative team-player mindset and willingness to participate in code reviews and knowledge sharing
- Eagerness to learn, coachability, and ability to act on feedback
- Competitive-programming experience through Codeforces, LeetCode, ICPC, or similar
- Exposure to LLM or agentic AI through academic projects or self-learning
- LangGraph experience with graphs, state machines, checkpointers, and HITL interrupts
- Experience with layered context, selectors and filters, summarization, compaction, and token budgeting
- Experience with multi-agent design, tool calling, structured output, and verification patterns
- Experience with Anthropic, OpenAI, or Azure OpenAI SDKs and prompt engineering
- Experience with Pydantic v2 and JSON Schema or typed contracts
- Experience with vector stores such as Qdrant or Azure AI Search and embeddings
- Knowledge of Model Context Protocol, including resources, tools, and Streamable HTTP
- Experience with CrewAI or Microsoft Agent Framework
- Experience with Temporal for long-running, resumable workflows
- Awareness of vLLM, paged attention, batching, quantisation, and model routing
- Recognized AI/ML or agentic-AI course or certification
- Cloud fundamentals certification in Azure, AWS, or GCP
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
In the 21st century, where technology brings people together through digitalization; Softobiz Technologies is combining the power of people, technology, and the market to Rethink Transformation & Enterprise Decisions. We are an avant-garde technology leader working at the heart of innovation to deliver cutting-edge technology solutions in digital transformation, product engineering, and cloud services. Our focus is always on accelerating the next age of digitalization by driving world-class product innovation and delivering future-ready solutions to achieve sustainable, operational, and mission-based goals for our client’s businesses.
