About the role

We're looking for a Python Developer who has built AI workflows end to end and

understands what separates a working demo from a production system: retrieval that

returns the right context, guardrails that hold, evaluation that tells you whether a change

helped or hurt, and pipelines that stay reliable at volume.

This role sits at the centre of ourAI-assisted automation and scaling efforts.

Key Responsibilities

Design, build, and operate AI workflows in Python, from prototype through to

production

Build RAG (Retrieval-Augmented Generation) pipelines — chunking, embeddings,

vector search, retrieval quality, and context management

Implement guardrails and safety controls around LLM outputs: input/output

validation, grounding, hallucination mitigation, prompt-injection defence, and

fallback behaviour

Build evaluation harnesses that measure output quality objectively rather than by

impression

Build AI-driven automation that removes repetitive manual work, and scale it

reliably as usage grows

Integrate LLMs and ML models into production: API endpoints, inference services,

orchestration, and supporting pipelines

Work with AI orchestration and agent frameworks, and integrate with external tools

and services

Instrument AI systems for observability — token usage, latency, cost, failure modes,

and output quality over time

Collaborate with data scientists and ML engineers to take models from notebook to

production

Work with data science and data engineering tools (Pandas, NumPy, Jupyter) for data

manipulation, analysis, and validation

Stay updated with a fast-moving AI ecosystem, and bring back what's worth adopting

Required Skills & Qualifications

3+ years of backend development experience in Python

Hands-on AI workflow experience

Strong command of Python and at least one Python web framework (FastAPI, Django,

or Flask)

Familiarity with MySQL and BigQuery, including schema design and query

optimization





Working knowledge of core AI engineering concepts: RAG, embeddings, vector

databases, guardrails, context management, and evaluation

Hands-on experience with AI tools and frameworks — LLM APIs, orchestration

frameworks (LangChain, LlamaIndex, or similar), and vector stores

Experience building AI-assisted automation and scaling it beyond a proof of concept

Solid understanding of RESTful APIs, HTTP, JSON, and integration with external

services

Experience implementing authentication, authorization, and security best

practices across services and APIs

Proven ability to optimize applications for performance, scalability, and

maintainability

Strong problem-solving, analytical, and debugging skills

Logical thinking and a solution-oriented approach — able to break down an

unfamiliar problem and work toward a workable answer

Excellent communication and collaboration abilities, and the ability to work

effectively with cross-functional teams — frontend, product, QA, data, and operations

Ability to learn new technologies quickly and adapt as business requirements change

B.E. / B.Tech / MCA or equivalent. Equivalent practical experience will be considered.

Good to Have (Advantage)

Experience with Docker or containerized deployments

Experience with local / open-source LLMs — running, optimizing, or integrating

models such as LLaMA, Mistral, or Gemma using serving tools like Ollama or vLLM,

in on-prem or containerized environments

How we work

We embrace AI-assisted engineering. We'd like you to use AI pair-programming tools

(Claude Code, Cursor, GitHub Copilot, or similar) as a force multiplier — while retaining

full ownership, review, and understanding of the code you ship.

Pay: From ₹800,000.00 per month

Advantages:

- Health insurance
- Provident Fund

Ability to commute/relocate:

- Kochi, Kerala: Reliably commute or planning to relocate before starting work (Required)

Application Question(s):

- What is your expected CTC?

Experience:

- Python: 3 years (Required)

Work Location: In person

📌 Python Developer — AI & Data (India)
🏢 IntrCity by RailYatri
📍 India