À propos
You'll work closely with product and engineering stakeholders to build an AI-driven application that integrates LLMs into structured workflows, retrieval systems, and automation pipelines. If you enjoy owning architecture decisions and solving practical problems with AI, this role will be a great fit.
What you'll work on
- Designing and building production AI systems using Python
- Integrating LLMs such as OpenAI, Claude, Gemini, or Llama into real workflows
- Developing Retrieval-Augmented Generation pipelines and semantic search systems
- Working with vector databases like Pinecone, Weaviate, FAISS, or Chroma
- Improving output quality through evaluation, guardrails, and hallucination reduction techniques
- Building scalable AI APIs using FastAPI or similar frameworks
- Deploying and maintaining AI services on AWS including ECS, Lambda, S3, API Gateway, and CloudWatch
- Optimizing latency, cost, security, and reliability of AI workloads
- Collaborating on long-term architecture, experimentation strategy, and system improvements
What we're looking for
- Strong software engineering background with 6–8+ years of experience
- Hands-on experience building production systems with LLMs
- Experience with LangChain, LlamaIndex, or similar orchestration frameworks
- Deep familiarity with embeddings, retrieval, and RAG design patterns
- Strong Python backend skills and API development experience
- Knowledge of PostgreSQL, Redis, and modern data infrastructure
-Comfortable deploying containerized services with Docker on AWS
- Ability to work independently and make architecture-level decisions
Nice to have
- Experience with autonomous agents or multi-step AI automation
- Fine-tuning or parameter-efficient tuning methods like LoRA
- LLM evaluation pipelines and observability tools
CI/CD workflows for AI systems
- Startup or SaaS product experience
Project details
This is a long-term collaboration with ongoing feature development and AI system optimization. We offer a competitive hourly rate and are open to milestone-based work for well-defined deliverables.
Contract duration of 3 to 6 months. with 40 hours per week.
Mandatory skills: Python, TensorFlow, Machine Learning, Data Science, Artificial Intelligence, FastAPI, AI Development, AI Agent Development
Compétences linguistiques
- English
Avis aux utilisateurs
Cette offre provient d’une plateforme partenaire de TieTalent. Cliquez sur « Postuler maintenant » pour soumettre votre candidature directement sur leur site.