ML Engineer

• Design, develop, and deploy production-grade ML and LLM-based applications

• Build and optimize Agentic RAG (Retrieval-Augmented Generation) systems

• Develop and manage LLM pipelines, including fine-tuning and prompt engineering

• Implement scalable AI architectures and agentic frameworks

• Work on model optimization, evaluation, and deployment pipelines

• Collaborate with cross-functional teams to translate business requirements into AI solutions

• Ensure security, compliance, and performance optimization in AI applications

• Lead technical discussions and provide architectural guidance

• 5–8+ years of experience in AI/ML engineering

• Minimum 4+ years in technical leadership or architectural roles

• Strong experience with Large Language Models (LLMs) such as OpenAI, Anthropic, Google Gemini, Llama, Mistral

• Expertise in fine-tuning techniques: LoRA, QLoRA, PEFT

• Hands-on experience in building Agentic RAG systems

• Experience with orchestration frameworks:

• LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel

• Strong understanding of Model Context Protocol (MCP) architecture

• Experience with vector databases:

• Pinecone, Weaviate, Chroma, Qdrant, FAISS

• Knowledge of embedding models and semantic search optimization

• Experience with tools such as:

• MLflow, LangSmith, Weights & Biases

• Vertex AI, SageMaker, Azure OpenAI Service

• Experience with cloud platforms:

• AWS Bedrock, GCP Vertex AI, Azure OpenAI

• Strong proficiency in Python

• Experience in:

• Async/concurrent programming

• API development (FastAPI, Flask)

• Agent memory systems and conversation management

• Knowledge of:

• Prompt injection prevention

• PII handling

• Secure RAG architecture

• Expertise in:

• Hybrid search, reranking, query expansion

• Context window optimization

• Strong communication and stakeholder management skills

• Ability to translate complex AI concepts into business solutions

• Proven leadership and decision-making capabilities

SA Technologies