Senior Engineer

Roles & Responsibilities

• Architect and lead the development of multi-agent AI systems using frameworks such as LangGraph, CrewAI, and AutoGen — enabling autonomous reasoning, tool use, inter-agent coordination, and adaptive decision-making at enterprise scale.
• Design and operationalize multimodal generative AI pipelines that unify text, image, tabular, and graph data using transformer-based architectures (BERT, CLIP, LLaVA, T5, Whisper, GPT-4o, Gemini) for rich, cross-modal intelligence.
• Build production-grade RAG and Graph-RAG systems integrating vector databases (Pinecone, pgvector, OpenSearch) and knowledge graphs (Neo4j, AWS Neptune) for semantic retrieval, entity-aware reasoning, and grounded generation.
• Lead LLM fine-tuning, prompt engineering, and model alignment strategies — including RLHF, PEFT, LoRA, and instruction tuning — to adapt foundation models for specialized enterprise use cases.
• Establish robust LLMOps and MLOps pipelines on Databricks (AWS) using MLflow, feature stores, prompt evaluation frameworks, model lineage tracking, and continuous retraining workflows to ensure reliable AI delivery.
• Develop high-performance Python backend services for LLM inference orchestration, async job handling, streaming responses, and distributed data workflows supporting high-throughput Gen AI operations.
• Engineer state, memory, and context management subsystems that enable agents to reason temporally, maintain session continuity, manage long-context windows, and coordinate across tools and modalities.
• Implement Responsible AI and AI governance practices — including bias detection, hallucination mitigation, explainability dashboards, output safety guardrails, and compliance with data ethics standards — ensuring transparency and fairness of deployed models.
• Apply traditional ML and statistical modeling (regression, clustering, forecasting, ensemble methods) in hybrid architectures alongside LLMs for interpretable, explainability-first decision systems.
• Continuously research, evaluate, and productionize advancements in generative modeling, agentic AI, multimodal transformers, and frontier foundation models — benchmarking against enterprise-scale performance and safety requirements.

All About Yo

• uMaster's or Bachelor's degree in Computer Science, AI/ML, or Engineering, with significant hands-on experience leading and delivering complex Gen AI or ML engineering programs in production environments
• .Expert-level, hands-on experience designing, building, and deploying large language model (LLM) applications, agentic systems, and RAG pipelines — from prototype to production
• .Deep proficiency with LLM ecosystems: OpenAI, Anthropic, Gemini, Hugging Face, LangChain/LangGraph, and open-source foundation models (LLaMA, Mistral, Falcon, etc.)
• .Strong command of Gen AI engineering patterns: prompt engineering, chain-of-thought reasoning, tool/function calling, vector embeddings, semantic search, and agent memory architectures
• .Solid applied knowledge of ML fundamentals — predictive modeling, deep learning (PyTorch, TensorFlow), and statistical techniques — used in tandem with Gen AI for hybrid, interpretable systems
• .Excellent Python engineering skills including async programming, API development (FastAPI), and building inference-ready microservices; SQL proficiency required
• .Hands-on experience with cloud AI infrastructure (AWS SageMaker, Bedrock, Azure OpenAI, or GCP Vertex AI) and familiarity with MLOps/LLMOps tooling (MLflow, Weights & Biases, etc.)
• .Strong analytical, communication, and stakeholder management skills — with the ability to translate complex Gen AI concepts into business value and lead cross-functional teams toward delivery