Note: The job is a remote job and is open to candidates in USA. Nexaminds develops artificial intelligence solutions focused on transforming businesses, streamlining processes, and driving growth. The LangChain Deployment AI Engineer will build and deploy production-grade generative and agentic AI systems, including LLM applications, RAG solutions, evaluation pipelines, and integrations. The role emphasizes secure, scalable, observable, maintainable deployments and collaboration with architects, engineering teams, and customers.
Responsibilities
- Translate approved **LangChain and agentic AI architectures** into maintainable, secure, scalable, and production-ready applications
- Build LLM-powered **assistants, copilots, chatbots, document-processing solutions, decision-support tools, and automated workflows**
- Develop deterministic and agentic workflows using **LangGraph**, including state management, routing, tool use, retries, checkpoints, memory, streaming, and failure recovery
- Design and implement **RAG pipelines**, including ingestion, chunking, embeddings, indexing, retrieval, reranking, grounding, citations, and access controls
- Integrate LLMs, embedding models, APIs, databases, search systems, vector stores, business applications, and custom tools through secure and maintainable interfaces
- Deploy AI applications using **Docker, Kubernetes, serverless, or managed cloud runtimes**, supporting environment promotion, rollback, autoscaling, resiliency, and disaster recovery
- Implement **LangSmith tracing, evaluation, monitoring, dashboards, alerts, and feedback workflows** to monitor model, tool, retrieval, latency, cost, and quality behavior
- Establish automated **quality engineering and evaluation processes**, including unit, integration, end-to-end, regression, adversarial, and load testing
- Build **offline and online evaluation frameworks**, golden datasets, quality thresholds, and release gates for prompts, models, retrieval systems, tools, and workflows
- Implement AI security and responsible AI practices, including **least privilege, IAM, encryption, secrets management, audit logging, PII safeguards, prompt-injection defenses, output controls, and human escalation**
- Optimize AI applications for **response quality, latency, throughput, reliability, context utilization, caching, model selection, and token consumption**
- Integrate AI solutions into **CI/CD pipelines** and establish reproducible deployment and release processes
- Create operational documentation, architecture updates, troubleshooting guides, runbooks, dashboards, alert thresholds, and incident procedures
- Partner with AI architects, Nexaminds delivery leaders, and customer stakeholders to communicate progress, risks, dependencies, and technical tradeoffs
- Participate in **design and code reviews**, mentor engineers, and support knowledge transfer to customer engineering and operations teams
- Monitor production systems, analyze feedback and failures, and continuously improve AI solution quality, reliability, performance, and cost
Skills
- Bachelor's degree in Computer Science, Engineering, Information Systems, or a related discipline, or equivalent practical experience
- Strong professional software engineering experience with **Python and/or JavaScript/TypeScript**, including API development, asynchronous processing, testing, packaging, dependency management, and code review
- Hands-on experience building production-grade AI agents using **LangChain and LangGraph**, including chains/runnables, tools, structured outputs, stateful workflows, streaming, persistence, and error handling
- Experience developing and deploying **LLM-powered applications** using commercial model APIs such as OpenAI, Anthropic, Google, or cloud-hosted equivalents, and/or open-source models
- Strong understanding of **Retrieval-Augmented Generation (RAG)**, including document ingestion, chunking, embeddings, vector search, metadata filtering, reranking, grounding, and citation patterns
- Experience working with at least one **vector database or search platform**, such as Pinecone, Weaviate, Milvus, pgvector/PostgreSQL, Elasticsearch/OpenSearch, Redis, Azure AI Search, or equivalent
- Experience deploying production-grade AI applications using **Docker and Kubernetes**
- Experience with at least one major cloud platform: **AWS, Microsoft Azure, or Google Cloud Platform (GCP)**
- Experience taking AI applications beyond POCs into production, including **CI/CD, environment management, monitoring, troubleshooting, and operational support**
- Hands-on experience with **LangSmith or comparable LLM tracing, evaluation, and observability tools**, including the ability to investigate quality, latency, cost, and tool/retrieval failures
- Familiarity with the **Agent Development Life Cycle (ADLC)** and production deployment of configurable AI agents
- Working knowledge of application security, including **IAM, secrets management, encryption, API security, auditability, privacy, and secure software development practices**
- Strong customer-facing communication, technical writing, and consulting skills, with the ability to explain technical tradeoffs to both engineering and business stakeholders
- Ability to work effectively in ambiguous environments and collaborate closely with AI architects, engineering teams, platform teams, security, data, and product stakeholders
- Experience with **LangChain enterprise products**, including LangSmith, Fleet, or Deep Agents
- Experience designing or implementing **multi-agent systems**, supervisor patterns, long-running workflows, durable execution, event-driven integrations, or human approval workflows
- Experience with cloud AI platforms such as **Amazon Bedrock, Azure AI Foundry/Azure OpenAI, or Google Vertex AI**
- Experience with managed Kubernetes platforms such as **EKS, AKS, or GKE**
- Experience with Infrastructure as Code and delivery tools such as **Terraform, Helm, GitHub Actions, GitLab CI, Jenkins, or Argo CD**
- Experience with observability platforms such as **OpenTelemetry, Datadog, Grafana, Prometheus, CloudWatch, Azure Monitor, or Google Cloud Operations**
- Knowledge of **LLM evaluation, model and prompt versioning, red teaming, adversarial testing, hallucination analysis, retrieval evaluation, and human feedback programs**
- Experience working in regulated or data-sensitive environments
- Relevant certifications in cloud, Kubernetes, security, data engineering, or AI/ML
Benefits
- Stock options
- Remote work options
- Flexible working hours
- Benefits above the law
- Access to mentorship and opportunities to learn and level up
Company Overview