Softobiz is Hiring AI Engineer Interns (Kochi) | Freshers Eligible

Role Summary

Softobiz is seeking five AI Engineering Interns to learn and contribute to production-grade agentic AI systems, working alongside experienced engineers. This is a hands-on, mentored internship focusing on multi-agent orchestration, context management, and large language model (LLM) integration. The opportunity is open to final-year students and recent graduates who possess outstanding computer science fundamentals, strong data structures and algorithms (DSA) skills, and practical Python proficiency.

Interns will work under the guidance of senior engineers on agent workflows and their underlying context architecture, contributing to real features while developing production-grade skills. The ideal candidate will have a strong academic record, sharp problem-solving abilities, 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 senior engineer guidance.
• Help model processes as stateful, resumable graphs that include branching, looping, retries, and checkpointing.
• Support the implementation of safe pause/resume functionalities and human-in-the-loop (HITL) checkpoints.

Context Engineering

• Learn and contribute to context management, including 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 to ensure 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 integrate retrieval mechanisms, such as vector search and embeddings, and code-intelligence techniques for working with large codebases.
• Contribute to model-routing experiments that balance task type, latency, and cost considerations.

Quality, Evaluation & Governance

• Help build evaluation and error-analysis loops, learning to use failures as feedback for reliability improvements.
• Assist in implementing verification and validation patterns and deterministic gates for agent outputs.
• Help maintain observability, auditability, and reproducibility of agent decisions and context.

Collaboration

• Work with platform/infrastructure engineers on deployment, inference, and persistence tasks.
• Participate in design reviews, code reviews, and Demo Friday sessions, sharing work and insights from experiments.

Required Technical Skills

• CS Fundamentals & DSA: Data structures, algorithms, complexity analysis, strong problem-solving.
• Programming: Python 3.10+ (async, typing); clean, idiomatic code.
• Agent Orchestration: LangGraph (graphs/state machines, checkpointers, HITL interrupts) is a plus.
• Context Engineering: Layered context, selectors/filters, summarisation & compaction, token budgeting are a plus.
• Agentic AI Development: Multi-agent design, tool calling, structured output, verification patterns are a plus.
• LLM Integration: Anthropic & OpenAI / Azure OpenAI SDKs, prompt engineering are preferred.
• Data Modelling: Pydantic v2, JSON Schema / typed contracts are preferred.
• Retrieval: Vector stores (e.g., Qdrant / Azure AI Search), embeddings are preferred.
• Context Protocol: Model Context Protocol (MCP) (resources/tools, Streamable HTTP) is preferred.
• Multi-agent Frameworks: CrewAI, Microsoft Agent Framework are preferred.
• Durable Workflows: Temporal (long-running, resumable flows) is preferred.
• Inference: vLLM awareness (paged attention, batching, quantisation), model routing are preferred.

Qualifications & Certifications

• Candidates should be pursuing or have recently completed a 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 are encouraged to apply; strong fundamentals are prioritized over years of experience.
• Strong data structures, algorithms, and problem-solving skills are essential; a competitive programming track record (Codeforces / LeetCode / ICPC / similar) is a significant advantage.
• Hands-on Python experience is required, along with any exposure to LLM / agentic AI through academic projects or self-learning, and a clear eagerness to delve into LangGraph and context engineering.

Preferred Certifications

• Any recognized 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 also beneficial.

Soft Skills & Cultural Fit

• Possess a strong analytical mindset with a structured approach to design, debugging, and root-cause analysis.
• Demonstrate clear written and verbal communication skills, able to explain technical concepts to both technical and non-technical audiences.
• Exhibit eagerness to learn, high coachability, and the ability to accept and act on feedback.
• Be a collaborative team player who contributes to shared standards, participates in code reviews, and facilitates knowledge sharing.