Junior AI Application Engineer — GenAI/SLM Applications
Location: Noida
Type: Full-Time, Permanent
Experience: 2+ years
Role Overview
We are looking for a Junior AI Application Engineer to join our GenAI delivery team and help build production LLM/SLM applications — including for air-gapped and on-prem environments. You will work on well-scoped pieces of larger features under the guidance of a senior Application Engineer or Technical Program Lead, with plenty of room to grow into full feature ownership.
Key Responsibilities
Build defined components of RAG pipelines, agents, and LLM/SLM-backed features from specs handed off by senior engineers.
Write and test Python code — API endpoints, data pipelines, and integration glue between LLM components and internal systems.
Assist with fine-tuning, quantizing, and evaluating SLMs under supervision; run benchmarks and document results.
Help set up and maintain vector store integrations (FAISS, Milvus, Weaviate, Qdrant) and local inference serving (vLLM, Ollama).
Containerize small services (Docker) and support deployment to cloud/on-prem targets alongside senior team members.
Keep JIRA stories updated, raise blockers early, and demo completed work in sprint reviews.
Use Claude Code / AI coding agents as your default way of writing code — learn to write
clear specs/prompts and to carefully review and test what the agent produces before it ships.
Required Skills & Experience
1-3 years of professional software engineering experience (internships count toward this).
Solid Python fundamentals; comfortable reading and debugging someone else’s code.
Some exposure to LLMs/GenAI — coursework, personal projects, hackathons, or prior work experience with LangChain/LlamaIndex, OpenAI/Anthropic APIs, or similar.
Basic understanding of REST APIs, git, and working in a codebase with others.
Curious and comfortable using AI coding tools (Claude Code or similar) as part of daily work, with a habit of reviewing generated code rather than accepting it blindly.
Willingness to learn Docker, cloud basics (AWS/Azure/GCP), and vector databases on the job.
Behavioural Expectations-
Eager to learn, asks good questions, and takes feedback well — this role is designed to grow you into a full Application Engineer.
Reliable on sprint commitments; keeps JIRA current and communicates blockers early rather than sitting on them.
Comfortable working alongside AI agents: writes clear instructions, checks the output carefully, doesn’t just copy-paste blindly.
Team player — collaborates well in a hybrid setup with distributed (US/India/APAC) colleagues.
Good to Have-
Personal projects, open-source contributions, or hackathon work involving LLMs/GenAI.
Exposure to Big Data tools (Spark/Hive) or basic ML/data science coursework.
Any experience, even academic, with model evaluation or prompt engineering.
Contribution to open source projects, academic papers published, filled patents What You will Gain.
Direct mentorship from senior Application Engineers and Technical Program Leads on real enterprise GenAI/SLM engagements.
Hands-on exposure to air-gapped/sovereign AI deployments — a niche, high-value skill set.
A fast track to owning full features independently within 12-18 months.