Software Engineer - Integration Specialist

Role overview

Core responsibilities

• Design and deploy GenAI and RAG applications using OpenAI, Claude, Llama, Qwen, and other open-source models.
• Build RAG pipelines covering ingestion, chunking, embeddings, vector databases, retrieval, reranking, prompt engineering, and generation.
• Develop voice bots and conversational AI integrating ASR, LLM/SLM, TTS, telephony, APIs, and business workflows.
• Build Python backend services and APIs; develop agentic AI, tool calling, workflow automation, and external integrations.
• Integrate databases, APIs, enterprise systems, and customer-specific data sources; work directly with customers to understand needs and troubleshoot.
• Take solutions from proof of concept to production; improve reliability, scale, latency, cost, performance, monitoring, and maintainability.
• Deploy and troubleshoot with Docker across cloud, on-premises, and customer environments; follow testing, CI/CD, Git, logging, review, and documentation practices.
• Collaborate with data science, ML engineering, product, infrastructure, and customer teams.

Qualifications

• 3+ years in software engineering, AI/ML engineering, data science, or GenAI, with hands-on development experience.
• Strong Python, backend development, software engineering fundamentals, and experience building and deploying RAG and LLM solutions.
• Experience with LangChain, LlamaIndex, Hugging Face, vector databases, embeddings, reranking, or equivalent technologies.
• Understanding of LLMs, prompt engineering, agentic AI, tool calling, MCP, and workflow automation.
• Experience with Voice AI or voice bots; ASR, TTS, telephony, and real-time conversational pipelines are noted.
• Experience with databases, REST APIs, FastAPI or Flask, microservices, Docker, backend architecture, and cloud or on-premises deployment.
• Knowledge of CI/CD, automated testing, Git, logging, monitoring, production debugging, and inference optimization.
• Problem-solving, communication, customer-facing, collaboration, and independent working skills are sought.

Preferred experience

• Kubernetes, cloud-native architectures, CI/CD, and production observability are good to have.
• Exposure to MCP, agentic AI frameworks, AI evaluation, model optimization, LLMOps/MLOps, customer deployments, proofs of concept, and enterprise integrations is good to have.