Job Description
SB-1486-AI Engineer Intern
0-1
Softobiz Kochi
Full-Time
AI Engineer Intern
🚀 Role Overview
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.
🎯 What Success Looks Like in This Role
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
Domain Skills & Technologies Must / Preferred
CS Fundamentals & DSA Data structures, algorithms, complexity analysis, strong problem-solving Must
Programming Python 3.10+ (async, typing); clean, idiomatic code Must
Agent Orchestration LangGraph — graphs/state machines, checkpointers, HITL interrupts Good to have
Context Engineering Layered context, selectors/filters, summarisation & compaction, token budgeting Good to have
Agentic AI Development Multi-agent design, tool calling, structured output, verification patterns Good to have
LLM Integration Anthropic & OpenAI / Azure OpenAI SDKs, prompt engineering Preferred
Data Modelling Pydantic v2, JSON Schema / typed contracts Preferred
Retrieval Vector stores (e.g. Qdrant / Azure AI Search), embeddings Preferred
Context Protocol Model Context Protocol (MCP) — resources/tools, Streamable HTTP Preferred
Multi-agent Frameworks CrewAI, Microsoft Agent Framework Preferred
Durable Workflows Temporal (long-running, resumable flows) Preferred
Inference vLLM awareness (paged attention, batching, quantisation), model routing Preferred
Qualifications & 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.
