Key skills
Backend developmentScalable system designAPI architectureDomain-Driven Design (DDD)MicroservicesgRPCRESTDatabasesPostgresMongoDBRedisClickhouseCloud infrastructureAWSTypeScriptGolangTestingUnit testingEnd-to-end testingLoad testingCypressPlaywrightk6ContainerizationDockerKubernetesDevOps practicesCI/CD pipelinesInfrastructure as Code (IaC)System monitoringDatadogGrafanaLarge Language Model (LLM) applicationsRetrieval-Augmented Generation (RAG)GPT-based solutionsPrompt engineeringAPI integrationOpenAIAnthropicGeminiMachine Learning frameworksPyTorchModel optimizationQuantizationModel distillationVector databasespgvectorWeaviatePineconeLLM inference stacksTensorRT-LLMVLLMllama.cppIssue trackingLinearSystem optimizationAnalytical skillsMLGenAILLMLlamaRAGCI/CDCommunicationCollaboration
About this role
TRACTIAN is transforming the industrial world by empowering frontline maintenance workers with innovative solutions. As a GenAI Lead Engineer, you will lead software projects, manage teams, and drive strategic decisions to enhance operational efficiency and contribute to the company's success.
Responsibilities:
- Lead Projects: Plan, schedule, and deliver software projects on time and at the highest quality
- Build Teams: Manage and mentor developers, fostering collaboration and high performance
- Drive Strategy: Make key decisions on backend architecture, scalability, and infrastructure
- Collaborate Cross-Functionally: Align software, product, engineering, and department goals for seamless execution
- Optimize Processes: Streamline workflows, solve technical challenges, and improve productivity
- Oversee Deployments: Ensure smooth, efficient deployments and system performance
Requirements:
- 8+ years in backend development specializing in scalable system design, API architecture (DDD), and microservices (gRPC, REST), with expertise in databases (Postgres, MongoDB, Redis, Clickhouse) and cloud infrastructure (AWS)
- Proficient in TypeScript and Golang, with extensive testing experience (unit, end-to-end, and load testing using Cypress, Playwright, k6)
- Skilled in containerization (Docker, Kubernetes) and DevOps practices, including CI/CD pipelines, infrastructure as code (IaC), and system monitoring (Datadog, Grafana)
- Experienced in developing and optimizing LLM applications, including Retrieval-Augmented Generation (RAG) and GPT-based solutions, with strong knowledge of deployment patterns, prompt engineering, and API integration (OpenAI, Anthropic, Gemini)
- Proficient in ML frameworks (PyTorch), optimization techniques (quantization, model distillation), and vector databases (pgvector, Weaviate, Pinecone)
- Experienced with LLM inference stacks (TensorRT-LLM, VLLM, llama.cpp) and developing RAG systems
- Proven ability to hire, mentor, and lead high-performing technical teams while setting technical direction and delivering impactful backend projects
- Strong track record of leading full development lifecycles, managing issue tracking (Linear), and delivering complex backend systems on time
- Strong problem-solving and analytical skills, with excellent communication to foster cross-functional collaboration and stakeholder alignment
- Experience in startups or high-growth environments, with deep expertise in system optimization tools and processes
- Bachelor's degree in Computer Science or Engineering