AI Engineer – Generative AI & Agentic AI

KData Inc.; United States; On-site; USD 140,000 - 190,000; Full time

Job summary

KData Inc. is seeking an AI Engineer specializing in Generative AI and agentic workflows.

You will design, develop, and operate production-grade GenAI applications, turning business requirements into reliable software using foundation models, enterprise data, APIs, and cloud services. You will collaborate with AI Architects, software engineers, data engineers, and security teams to deliver secure, observable AI capabilities such as conversational assistants and document intelligence.

Job description

AI Engineer – Generative AI & Agentic AI

The AI Engineer designs, develops,integrates, tests, and operates production-ready AI applications, with a focuson Generative AI (GenAI), Retrieval-Augmented Generation (RAG), and agenticworkflows. The role turns product and business requirements into reliablesoftware using foundation models, enterprise data, APIs, and cloud services.The AI Engineer works closely with AI Architects, software engineers, dataengineers, product teams, and security stakeholders to deliver useful, secure,observable, and cost-aware AI capabilities such as conversational assistants,document intelligence, summarization, and knowledge Q&A.

Key Responsibilities

• · Develop maintainable, testedPython services and components for GenAI applications, data processing,retrieval, and model integration.
• · Implement prompt templates,structured outputs, tool/function calling, and model-provider integrations;evaluate and iterate based on task requirements.
• · Build end-to-end RAG pipelinesincluding document ingestion, parsing, cleaning, metadata extraction, chunking,embedding, indexing, retrieval, reranking, and context construction.
• · Integrate vector and hybridsearch systems; tune retrieval and grounding quality using relevant evaluationdatasets and metrics.
• · Develop agentic workflows withbounded tool use, state management, routing, retries, error handling, and humanapproval where needed.
• · Integrate enterprise APIs,databases, document repositories, and business systems while respectingauthentication, permissions, and data boundaries.
• · Build application APIs and userinterfaces or prototypes using frameworks such as FastAPI and Streamlit;collaborate with frontend engineers for production interfaces.
• · Deploy and operate AI servicesin cloud environments; use containers, CI/CD, configuration management, andenvironment separation.
• · Instrument applications withlogs, traces, metrics, and feedback capture; monitor quality, latency, tokenusage, failures, and cost.
• · Write unit, integration,retrieval, evaluation, and regression tests; participate in code reviews,documentation, and technical knowledge sharing.
• · Apply security and responsibleAI practices, including prompt-injection defenses, sensitive-data handling,output validation, and safe tool permissions.

Requirements

Mandatory Skills & Experience

1. Python & Software Engineering

• · Strong practical Python skills,including writing modular, readable, maintainable, and testable code.
• · Experience with common Pythonlibraries such as NumPy, pandas, and Pydantic; familiarity with typing,packaging, virtual environments, and dependency management.
• · Working knowledge of REST APIs,JSON, asynchronous programming (async/await), concurrency, exception handling,and API integration.
• · Familiarity with Git, codereviews, unit testing (e.g., pytest), debugging, and basic software designprinciples.

2. Generative AI & LLM Application Development

• · Hands-on experience buildingLLM-powered applications such as chat, summarization, extraction, documentassistants, or question-answering systems.
• · Understanding of tokens,context windows, prompt design, system instructions, temperature and othergeneration parameters, structured generation, and model limitations.
• · Experience integrating hostedor open-source LLMs through APIs or model-serving endpoints.
• · Ability to use streaming,caching, batching where appropriate, and asynchronous processing to improveresponsiveness and manage costs.

3. RAG, Embeddings & Search

• · Practical experienceimplementing RAG: document loading, parsing, chunking, embedding generation,vector indexing, retrieval, context assembly, and grounded response generation.
• · Understanding of denseretrieval, keyword search (BM25), hybrid search, metadata filtering, queryrewriting, and reranking.
• · Familiarity with vector/searchtechnologies such as FAISS, pgvector, Pinecone, Qdrant, Weaviate, Chroma,Milvus, Elasticsearch/OpenSearch, or cloud equivalents.
• · Ability to evaluate retrievaland answer quality using test questions, relevance/groundedness checks, andfeedback.

4. AI Frameworks & Agentic Workflows

• · Experience with at least onecurrent LLM application framework, such as LangChain or LangGraph; familiaritywith framework abstractions and trade-offs.
• · Experience or workingfamiliarity with agentic workflow frameworks such as Microsoft Agent Framework/ AutoGen, Semantic Kernel, or CrewAI.
• · Understanding of tool/functioncalling, workflow state, routing, task decomposition, memory, retries, andhuman-in-the-loop patterns.
• · Familiarity with MCP (ModelContext Protocol) and secure integration of agents with tools or externalservices is desirable; where required by the role, treat as a core skill.
• · Ability to implement bounded,testable workflows rather than relying on unconstrained autonomous behavior.
• · Hands-on deployment experienceon at least one of AWS, Microsoft Azure, or Google Cloud Platform, withwillingness and ability to work across cloud environments.
• · AWS familiarity: AmazonBedrock, SageMaker, S3, Lambda, ECS/EKS, IAM, and CloudWatch.
• · GCP familiarity: Vertex AI,Gemini, Cloud Storage, Cloud Run, GKE, BigQuery, and Cloud IAM.
• · Understand cloud fundamentalsincluding compute, storage, networking basics, identity, secrets, logging, anddeployment configuration.

6. APIs, Data & Application Integration

• · Experience integrating AIcomponents with REST APIs, SQL/NoSQL databases, enterprise data sources, andapplication services.
• · Understanding of datapreprocessing, document formats, metadata, access permissions, and datafreshness for retrieval systems.
• · Familiarity with FastAPI or asimilar Python API framework; Streamlit or equivalent is useful for prototypesand internal tools.

7. Quality, Security & Observability

• · Ability to test AI featuresbeyond conventional software tests, including prompt/model regression,retrieval relevance, groundedness, and safety.
• · Familiarity with tracing andmonitoring tools such as Langfuse, LangSmith, OpenTelemetry, or cloud-nativeobservability.
• · Understanding of promptinjection, data leakage, output validation, moderation, least-privilege toolaccess, and secure handling of credentials.
• · Ability to track operationalmetrics such as latency, errors, token consumption, throughput, and cost.

Good‑to‑Have Skills

• · Model customization:fine-tuning, LoRA/QLoRA, PEFT, quantization, prompt tuning, or working withHugging Face Transformers.
• · Experience with PyTorch orTensorFlow and foundational ML/NLP concepts, including model training orinference workflows.
• · Containerization with Docker;Kubernetes or managed container services; CI/CD pipelines and infrastructure ascode.
• · Multimodal applicationsinvolving image, audio, speech, or vision-language models.
• · Experience with model providersand model families such as OpenAI, Anthropic, Google Gemini, Meta Llama,Mistral, or Cohere.
• · Experience with data processingat scale, distributed processing, or tools such as Dask or Spark.
• · Exposure to AI governance andrisk practices, including NIST AI RMF, ISO/IEC 42001, or regulated-domainrequirements.

Qualifications & Experience

• · Bachelor’s degree in ComputerScience, Engineering, Data Science, or a related discipline, or equivalentpractical experience.
• · Typically 3+ years of software,data, or AI/ML engineering experience; practical GenAI application experienceis strongly preferred. Adjust the level based on hiring needs.
• · Demonstrable project orprofessional experience delivering software components; production deploymentexperience is an advantage.
• · Strong problem-solving skills,curiosity, collaboration, and ability to learn evolving AI technologies.