Posted on: 05/01/2026
Description :
- Architect, develop, and deploy robust LLM-based applications, including custom pipelines, prompt engineering, and fine-tuning when needed.
- Build RAG systems using embedding models, vector search, and optimized retrieval pipelines.
- Design and manage Vector Databases (e.g., Pinecone, Chroma, Weaviate, Qdrant) to support scalable semantic search and knowledge retrieval.
- Develop high-quality Python applications, APIs, and automation workflows that integrate AI models into
production systems.
- Implement data pipelines for ingestion, preprocessing, metadata enrichment, and evaluation.
- Optimize LLM performance, latency, cost, and accuracy through model selection, quantization, caching, and other engineering strategies.
- Deploy AI workloads to cloud platforms (AWS/Azure), including serverless and container-based environments.
- Conduct comprehensive testing, debugging, and performance tuning for AI services.
- Maintain documentation across the AI development lifecycledesign, experiments, deployment, and monitoring.
- Stay current with emerging AI research and tooling and apply best practices to enhance internal AI capabilities.
What We're looking for :
Required Qualifications :
- 4+ years of professional experience in software engineering, ML engineering, or AI application development.
- Strong hands-on experience with Python, FastAPI/Flask, and microservices.
- Expertise in LLMs (GPT, Llama, Mistral, etc.) and modern AI frameworks.
- Experience building RAG pipelines, including embeddings, retrievers, chunking strategies, and context optimization.
- Proficiency with Vector Databases such as Pinecone, Chroma, Weaviate, Qdrant, FAISS, etc.
- Strong understanding of prompt engineering, model orchestration, and evaluation techniques.
- Solid experience with REST APIs, asynchronous processing, and cloud-native architecture.
- Knowledge of SQL and NoSQL databases and data modeling.
- Familiarity with CI/CD pipelines, Git, and automated testing.
- Understanding of MLOps principles, feature stores, and model deployment workflows.
- Strong debugging skills, analytical thinking, and attention to detail.
- Excellent communication and collaboration abilities.
Nice to Have :
- Knowledge of LangChain, LlamaIndex, or similar orchestration frameworks.
- Understanding of AWS/Azure AI services, serverless architecture, and containerization (Docker/Kubernetes).
- Familiarity with data engineering pipelines, ETL processes, and streaming frameworks.
- Experience with Generative AI for text, speech, or multimodal applications.
- Background in NLP, information retrieval, or knowledge graphs.
What's In It For You :
- Full benefits package.
- Paid time off (PTO).
- Holiday pay.
- Career growth and learning opportunities in advanced AI technologies.
- Opportunity to shape the future of AI in the mortgage and financial services domain.
Did you find something suspicious?