AI Engineer
Location: UL Cyber Park , Calicut
Department: Engineering / AI & Machine Learning
Employment Type: Full-time
Greeting from Tranetech Software Solution LLC
About the Role
We're looking for an AI Engineer to design, build, and deploy production-grade applications powered by Large Language Models (LLMs). You'll work on everything from prompt engineering and Retrieval-Augmented Generation (RAG) pipelines to fine-tuning, evaluation, and scaling AI systems that solve real business problems. This is a hands-on role for someone who enjoys taking LLM capabilities from prototype to production.
What You'll Do
- Design, implement, and optimize RAG pipelines (chunking strategies, embeddings, vector databases, retrieval tuning, re-ranking)
- Integrate and fine-tune LLMs (open-source and proprietary APIs) for specific use cases
- Build and maintain prompt engineering frameworks, evaluation harnesses, and testing pipelines to measure output quality, hallucination rates, and latency
- Develop agentic workflows and tool-use integrations (function calling, multi-step reasoning, orchestration)
- Own the full lifecycle of LLM features: data preparation, model selection, deployment, monitoring, and iteration
- Work with vector databases and manage embedding pipelines at scale
- Collaborate with product and data teams to translate business requirements into AI-powered features
- Implement guardrails, safety filters, and evaluation metrics to ensure reliable and responsible AI outputs
- Optimize for cost, latency, and performance across inference infrastructure
- Write clean, well-tested, production-grade Python code to support all of the above
- Stay current with the fast-moving LLM landscape and evaluate new models, tools, and techniques
Required Qualifications
- 2–5+ years of experience in software engineering, ML engineering, or a related field
- Hands-on experience building applications using LLMs (GPT, Claude, Llama, Mistral, Gemini, etc.)
- Practical experience implementing RAG systems, including embeddings and vector search
- Strong Python skills, with the ability to design and ship production-quality code independently
- Familiarity with ML/AI libraries (PyTorch, TensorFlow, Hugging Face Transformers, scikit-learn)
- Experience with LLM orchestration frameworks
- Solid understanding of prompt engineering, context window management, and token optimization
- Experience with cloud platforms (AWS, GCP, or Azure) and containerization (Docker/Kubernetes)
- Familiarity with API integration and building scalable backend services
Tools & Technologies
- LLM Providers / Models: OpenAI, Anthropic Claude, Meta Llama, Mistral, Google Gemini, Cohere
- Orchestration Frameworks: LangChain, LlamaIndex, Semantic Kernel, Haystack, CrewAI, AutoGen
- Vector Databases: Pinecone, Weaviate, Qdrant, Milvus, pgvector, Chroma, FAISS
- ML/DL Frameworks: PyTorch, TensorFlow, Hugging Face Transformers, scikit-learn
- Fine-Tuning & Optimization: LoRA/QLoRA, PEFT, RLHF, DeepSpeed, vLLM, TensorRT-LLM
- Evaluation & Observability: RAGAS, TruLens, DeepEval, LangSmith, Weights & Biases, Arize, PromptLayer
- Data Processing: Apache Spark, Airflow, Pandas, NumPy
- Infrastructure & Deployment: Docker, Kubernetes, AWS (SageMaker, Bedrock), GCP (Vertex AI), Azure AI Studio, Terraform
- APIs & Backend: FastAPI, Flask, REST/GraphQL APIs, gRPC
- Version Control & CI/CD: Git, GitHub Actions, MLflow, DVC
Nice to Have
- Experience fine-tuning or instruction-tuning open-source LLMs
- Knowledge of evaluation frameworks (RAGAS, TruLens, DeepEval, or custom eval pipelines)
- Experience with agentic architectures and multi-agent systems
- Background in MLOps / LLMOps practices (model versioning, monitoring, CI/CD for ML)
- Understanding of AI safety, responsible AI practices, and data privacy considerations
- Experience with streaming inference and real-time chat applications
Selection Advantage
- Strong Python coding ability — candidates who can demonstrate solid software engineering fundamentals in Python (clean architecture, testing, debugging, performance optimization) beyond just calling APIs will be given priority in the selection process.
Pay: ₹450,000.00 - ₹900,000.00 per year
Benefits:
- Health insurance
- Leave encashment
- Paid sick time
- Paid time off
- Provident Fund
Work Location: In person
