AMPITY INFOTECH

AI Engineer

LLM / GenAI Systems | ML & Model Engineering | Applied AI Delivery

Location: Remote (India)

Employment Type: Full-time

Team: Client Delivery Engineering

Reports To: Tech Lead / Engagement Lead

About Ampity Infotech

Ampity Infotech is a cloud and DevOps engineering firm that helps growing companies design, build, and operate production-grade software and infrastructure on AWS. We work directly with client engineering and leadership teams, and we build AI-powered capabilities into client products as a core part of our delivery, not as a side experiment.

Role Summary

As an AI Engineer on Ampity's delivery team, you will design, build, and ship AI-powered capabilities for client products. The work spans applied LLM/GenAI engineering (RAG pipelines, agentic workflows, prompt design, evaluation) and classical ML/data science (model training, fine-tuning, feature engineering, deployment) depending on what an engagement calls for. You will be accountable for how these systems perform in production, meaning accuracy, latency, cost, and reliability, not just for a working prototype.

What You'll Own

- Design and build LLM/GenAI-powered features: RAG pipelines, agentic or tool-calling workflows, prompt design, and integration with model providers (OpenAI, Anthropic, AWS Bedrock, etc.).
- Build, fine-tune, and evaluate ML models where a classical or statistical approach fits the problem better than an LLM, including data preprocessing and feature engineering.
- Design and run evaluation frameworks (offline evals, golden datasets, human-in-the-loop review) to measure accuracy, hallucination rate, and regressions before and after changes.
- Deploy and operate AI/ML systems in production on AWS (SageMaker,



Bedrock, Lambda, or EKS), with monitoring for drift, latency, and cost.
- Own data pipelines that feed models and retrieval systems: ingestion, chunking, embeddings, and vector store management.
- Apply security and responsible-AI practices: data handling, PII protection, prompt-injection defenses, and guardrails for AI-facing product surfaces.
- Communicate model behavior, limitations, and trade-offs clearly to client engineering teams and non-technical stakeholders.
- Produce implementation notes and handover documentation so client teams can operate and extend what you build.
- Use AI-assisted coding tools as part of your own workflow, with the judgment to verify their output before it reaches production.

Required Qualifications

- 2-4 years of hands-on experience building and shipping AI/ML systems to production, not just research notebooks or proofs of concept.
- Practical experience with LLM APIs (OpenAI, Anthropic, AWS Bedrock) and at least one GenAI framework such as LangChain or LlamaIndex.
- Solid Python skills, including experience with ML/data libraries (pandas, NumPy, scikit-learn, PyTorch, or TensorFlow).
- Experience building or operating RAG pipelines and working with vector databases or embedding stores (Pinecone, pgvector, OpenSearch, or similar).
- Understanding of model evaluation methodology: metrics, test sets,



and how to detect regressions or hallucinations.
- Working knowledge of cloud platforms (AWS preferred) for deploying and serving models.
- Ability to explain model behavior, limitations, and trade-offs clearly to both technical and non-technical stakeholders.

Nice to Have

- Experience fine-tuning open-source or foundation models (LoRA/PEFT, instruction tuning).
- Experience with agentic frameworks (LangGraph, AutoGen, or custom tool-calling orchestration).
- Familiarity with MLOps tooling (MLflow, SageMaker Pipelines, Weights & Biases).
- Exposure to data engineering (Airflow, Spark, dbt) for building training or retrieval datasets.
- Prior experience in a client-facing consulting or applied AI product workplace.

What We Value Ampity looks for AI engineers who ship systems that hold up in production, not just demos that work once. In practice, that means we weigh these traits heavily in this role:

- AI fluency with scepticism you use AI and model outputs to move faster, and you know how to verify them before they reach production.
- Production ownership — you understand incidents, cost, drift, and maintenance, not just initial delivery.
- Trade-off reasoning — you compare a classical ML approach, an LLM, or a simpler rule-based system against the client's real constraints, rather than defaulting to the newest technique.
- Clarity — you can explain a model's behavior and limitations, including its uncertainty, to a teammate and to a client.
- Knowledge transfer — you make the team and the client stronger rather than accumulating private expertise.

How to Apply Apply on – [email protected]

📌 AI Engineer (Pune)
🏢 Ampity Infotech
📍 Pune