AI Engineering Intern (Python)

About the role

Apply via Valura.AI’s official careers site. Valura.AI is hiring an AI Engineering Intern (Python) for 3 to 6 months (full-time preferred), with locations listed as Chennai, GIFT City (Gandhinagar), or Remote. The intern will work on a Python multi-agent microservice that powers in-app research, portfolio explanation, and customer support on Valura’s regulated investing platform. The posting date on the careers page is 27 Jul 2026; the listing was still live and accepting applications when checked on 15 Nov 2026. The careers page also shows “0 - 3 yrs Exp.” alongside the intern title; this is included as stated, not as a 0–1 year cap. Compensation is described only as a competitive stipend based on experience. High performers may transition to full-time AI Engineer roles.

Responsibilities

• Build and extend agents in the multi-agent orchestrator: research, portfolio analysis, market commentary, support
• Design tools and MCP integrations that let agents pull real data (portfolios, market feeds, ledger balances) instead of guessing
• Write and improve prompts as versioned, tested artifacts
• Build retrieval pipelines over fund documents, factsheets, research notes and regulatory content
• Build evaluation harnesses: golden datasets, regression suites, LLM-as-judge scoring
• Add tracing and observability so the team can see why an agent said what it said
• Work on guardrails: grounding checks, refusal behaviour, and making sure the system never invents a number
• Integrate the AI layer with chat surfaces (in-app, WhatsApp, Telegram) and the APIs behind them
• Optimise for latency and cost: caching, model routing, prompt size, streaming
• Ship to staging and production with Docker on AWS, and help debug it when it misbehaves

Requirements

• Required: Solid Python; ability to read someone else's code and extend it without rewriting it
• Hands-on experience calling LLM APIs, even if only from side projects
• Basic SQL and comfort with data: joining, cleaning, sanity-checking
• Comfort with Git and the terminal
• Clear thinking and clear writing
• Genuine skepticism; if a model gives an answer, the instinct should be to verify it
• Nice to have: RAG or vector-database experience (pgvector, FAISS, Qdrant, or similar)
• Agent frameworks, tool calling, or MCP
• Evaluation experience measuring model quality
• FastAPI, Docker, or any cloud deployment exposure
• Interest in markets and investing (finance experience is not required)

Benefits

• Competitive stipend based on experience
• High performers may transition to full-time AI Engineer roles
• Duration 3 to 6 months (full-time preferred)

Required Skills