Python / LLM EngineerMid-Senior

Narix Labs; Jaipur; On-site; INR 350,000 - 550,000; Full time

Job summary

Narix Labs is seeking a Python/LLM Engineer to own the AI capability of Bispy, an LLM coaching assistant grounded in behavioural-science methodology. You’ll lead prompts, context assembly, and retrieval over Qdrant, building an end-to-end coaching layer with emphasis on evaluation and cost control.

Join a team delivering real client work with weekly outputs, in an on-site Jaipur-based setting. You’ll work with Claude, GPT, Gemini, and open-weight APIs, shaping a measurable, auditable AI product

Qualifications

• 3+ years of production Python, with 1+ year building LLM-backed features that shipped.
• Hands-on retrieval/RAG experience — vector stores (Qdrant or similar), embeddings, and the failure modes of both.
• Treat evaluation as engineering, not vibes: describe how you’d catch a quality regression automatically.
• Comfort with the full API landscape (Claude, GPT, Gemini, open-weights) and choosing empirically.
• Strong written communication — model behavior gets documented, not remembered.

Responsibilities

• Own the LLM coaching layer end to end: prompts, context assembly, retrieval, fallbacks, and cost control
• Build and tune retrieval over Qdrant: chunking, embeddings, hybrid search, and relevance you can measure
• Maintain evaluation as a first‑class system — golden datasets, automated scoring, regression gates on every change
• Develop the assessment scoring/ML pipeline in Python, with results that are explainable to non‑engineers
• Keep data boundaries structural: sensitive assessment data gets the minimum‑necessary treatment, always

Skills

Python

LLM features

Retrieval (RAG)

Embeddings

Evaluation engineering

API awareness

Tools

Qdrant

PostgreSQL

RAGE evals

Job description

Engineering

Python / LLM Engineer

Own the AI layer of a live coaching platform: an LLM assistant grounded in a real behavioural-science methodology, retrieval over Qdrant, and the evaluation discipline that keeps it honest.

Jaipur, India

All roles are based in Jaipur, India — on-site only, not remote.

• remote friendly (IST) Full-timeBispy bot, Qdrant retrieval, AI coaching, scoring/ML

The role

You’ll own the AI capability of a production platform: Bispy, an LLM coaching assistant that must stay inside a client’s behavioural-science methodology — an LLM freelancing generic advice would undermine the intellectual property the product is built on. The work is the unglamorous, decisive part of applied AI: retrieval quality over Qdrant, prompt and context engineering, evaluation suites that catch regressions before users do, and the scoring/ML pipeline behind assessments.

Role details

What you’ll do

• Own the LLM coaching layer end to end: prompts, context assembly, retrieval, fallbacks, and cost control
• Build and tune retrieval over Qdrant: chunking, embeddings, hybrid search, and relevance you can measure
• Maintain evaluation as a first‑class system — golden datasets, automated scoring, regression gates on every change
• Develop the assessment scoring/ML pipeline in Python, with results that are explainable to non‑engineers
• Keep data boundaries structural: sensitive assessment data gets the minimum‑necessary treatment, always

What you bring

• 3+ years of production Python, with 1+ year building LLM‑backed features that shipped
• Hands‑on retrieval/RAG experience — vector stores (Qdrant or similar), embeddings, and the failure modes of both
• You treat evaluation as engineering, not vibes: you can describe how you’d catch a quality regression automatically
• Comfort with the full API landscape (Claude, GPT, Gemini, open‑weights) and choosing empirically
• Strong written communication — model behavior gets documented, not remembered

Nice to have

• Classical ML fundamentals (scikit‑learn‑level) for scoring models beyond the LLM
• Experience constraining LLMs to a domain methodology or brand voice with measurable adherence
• Voice or real‑time AI exposure

You’ll work with

PythonLLM APIsQdrantRAGEvalsPostgreSQL

What you get

Senior‑led delivery: your work is reviewed by people who’ve shipped production systems, and you see how they think

An AI‑native workflow — modern AI tooling is standard practice here, with human review as the quality bar

Real products in production: client work that ships weekly and gets used, not internal demos

Async‑first, writing‑heavy culture on IST, with deliberate US/EU overlap instead of late‑night calls

Competitive compensation, reviewed on outcomes

How we hire

Four steps, no gauntlet

1. Send the form on the role page — the cover note and links matter far more than a perfectly formatted CV.
2. Intro call (30 min): A real conversation about the role, your work, and whether the fit is mutual. No trick questions.
3. Practical round: A scoped, role‑relevant exercise or portfolio deep‑dive — designed to respect your time, not a weekend of free work.
4. Founder conversation & offer: You meet the person you’ll actually work with. If it’s a yes on both sides, we move fast.